{"id":"https://openalex.org/W4412610388","doi":"https://doi.org/10.1109/hpcc64274.2024.00023","title":"End-to-End Dense Video Captioning Model Based on Multimodal Feature Fusion","display_name":"End-to-End Dense Video Captioning Model Based on Multimodal Feature Fusion","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412610388","doi":"https://doi.org/10.1109/hpcc64274.2024.00023"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc64274.2024.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051024698","display_name":"Shixin Peng","orcid":"https://orcid.org/0000-0002-0916-180X"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixin Peng","raw_affiliation_strings":["Central China Normal University,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101671109","display_name":"Ting Xiong","orcid":"https://orcid.org/0000-0001-6752-4640"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Xiong","raw_affiliation_strings":["Central China Normal University,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103741898","display_name":"Jingying Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingying Chen","raw_affiliation_strings":["Central China Normal University,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40963666"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3909372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8741527795791626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7659621238708496},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7046537399291992},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6306564807891846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5237880945205688},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5038372874259949},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44853243231773376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3563506603240967},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10176634788513184}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8741527795791626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659621238708496},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7046537399291992},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6306564807891846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5237880945205688},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5038372874259949},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44853243231773376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3563506603240967},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10176634788513184},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc64274.2024.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2119717200","https://openalex.org/W2507009361","https://openalex.org/W2755876276","https://openalex.org/W2948358897","https://openalex.org/W2963351113","https://openalex.org/W2963524571","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2967142205","https://openalex.org/W2968104955","https://openalex.org/W2985144848","https://openalex.org/W2985185987","https://openalex.org/W3034815696","https://openalex.org/W3092161114","https://openalex.org/W4214663214","https://openalex.org/W4386065554","https://openalex.org/W4386066385","https://openalex.org/W4393404832","https://openalex.org/W6679434410","https://openalex.org/W6680796580","https://openalex.org/W6727253422","https://openalex.org/W6755207826","https://openalex.org/W6784094891","https://openalex.org/W6858057904"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4404782863"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,38,84],"dense":[3,72],"video":[4,73,86],"captioning":[5,74,107],"is":[6,122,140],"to":[7,13,35,91,113,124],"generate":[8],"multiple":[9],"text":[10,61],"descriptions":[11],"related":[12],"different":[14],"timestamps":[15],"from":[16],"a":[17,22,131],"video.":[18],"Traditional":[19],"methods":[20],"adopt":[21],"two-stage":[23],"\"localize-then-describe\"":[24],"approach":[25],"but":[26],"overlook":[27],"the":[28,85,92,126,137,149,154],"correlation":[29],"between":[30],"localization":[31],"and":[32,52,81,109,159],"captioning,":[33],"leading":[34],"inaccurate":[36],"predictions":[37],"event":[39,110],"boundaries.":[40],"Additionally,":[41],"existing":[42],"models":[43],"often":[44],"rely":[45],"solely":[46],"on":[47,148],"visual":[48],"information,":[49],"neglecting":[50],"audio":[51],"textual":[53,82],"subtitle":[54],"cues,":[55],"which":[56],"results":[57],"in":[58,161],"less":[59],"accurate":[60],"descriptions.":[62,164],"To":[63],"address":[64],"these":[65],"issues,":[66],"this":[67,77],"paper":[68],"proposes":[69],"an":[70],"end-to-end":[71,115],"model.":[75],"In":[76],"model,":[78],"visual,":[79],"audio,":[80],"features":[83,129],"are":[87],"used":[88],"as":[89],"inputs":[90],"encoding":[93],"layer,":[94],"processed":[95],"through":[96,143],"three":[97,127],"structurally":[98],"identical":[99],"Deformable":[100],"Transformer":[101],"encoders.":[102],"Three":[103],"parallel":[104],"tasks\u2014localization":[105],"head,":[106,108],"counter\u2014are":[111],"designed":[112],"facilitate":[114],"training.":[116],"A":[117],"multimodal":[118],"feature":[119,134],"fusion":[120],"module":[121],"introduced":[123],"integrate":[125],"modal":[128],"into":[130],"temporally":[132],"coherent":[133],"vector.":[135],"Finally,":[136],"model\u2019s":[138],"performance":[139],"further":[141],"enhanced":[142],"reinforcement":[144],"learning.":[145],"Extensive":[146],"experiments":[147],"ActivityNet":[150],"dataset":[151],"demonstrate":[152],"that":[153],"proposed":[155],"model":[156],"outperforms":[157],"PDVC":[158],"MDVC":[160],"generating":[162],"higher-quality":[163]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}